PHP制作百度词典查词采集器

百度dict 采集样本

写的采集百度dict词典翻译后的所有结果数据，当然附带了13.5w单词库和采集简单的案例，这里我把写出的主要类dict.class.php放出来，项目地址http://github.com/widuu/baidu_dict，有需要的直接fork就可以了~么么哒，这东西用的人很少，所以有用的兄弟拿走了哈~

 音标
	 *				"pro"	 => 发音
	 *				"example"=> 例句
	 *				"explain"=> 简明释义
	 *				"synonym"=> 同反义词
	 *				"phrase" => 短语数组
	 *			)
   *
	 */
	public function content($word){
		 $this -> word = $word;
		 $symbol = $this -> Pronounced();
		 $pro	 = $this->getSay();
		 $example = $this -> getExample();
		 $explain = $this -> getExplain();
		 $synonym = $this -> getSynonym();
		 $phrase = $this -> getPhrase();
		 $result = array(
				"symbol" => $symbol,		//音标
				"pro"	 => $pro,			//发音
				"example"=> $example,		//例句
				"explain"=> $explain,		//简明释义
				"synonym"=> $synonym,		//同反义词
				"phrase" => $phrase 		//短语数组
			);
		return $result;
	}


	/**
   * 远程获取百度翻译内容
   * get function curl
   * retun string
   *
	 */

	private function getContent(){
 		$useragent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0";
 		$ch = curl_init();
 		$url = "http://dict.baidu.com/s?wd=".$this->word;
 		curl_setopt($ch, CURLOPT_URL, $url);
 		curl_setopt($ch, CURLOPT_USERAGENT,$useragent);
		curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE); 
		curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); 
		curl_setopt($ch, CURLOPT_HTTPGET, 1);
		curl_setopt($ch, CURLOPT_AUTOREFERER,1);
		curl_setopt($ch, CURLOPT_HEADER, 0); 
		curl_setopt($ch, CURLOPT_TIMEOUT, 30);
		$result = curl_exec($ch);
		if (curl_errno($curl)) {
			echo 'Errno'.curl_error($curl);
		}
		curl_close($ch);
		return $result;
	}


	/**
   * 获取百度翻译发音
   * retun array(英，美)
   *
	 */

	private function Pronounced(){
		$data = $this -> getContent();
		preg_match_all("/\"EN\-US\"\>(.*)\<\/b\>/Ui",$data,$pronounced);
		return array(
			'en' => $pronounced[1][0],
			'us' => $pronounced[1][1]
		);
	}

	/**
	 * 获取百度翻译发音
	 * return array(英，美)
	 *
	 */

	private function getSay(){
		$data = $this -> getContent();
		preg_match_all("/url=\"(.*)\"/Ui",$data,$pronounced);
		return array(
			'en' => $pronounced[1][0],
			'us' => $pronounced[1][1]
		);	
	}

	/**
   * 获取百度翻译例句
   * return array() 多维数组 例句
   * 
	 */

	private function getExample(){
		$str = "";
		$data = $this -> getContent();
		preg_match_all("/var example_data = (.*)\]\;/Us",$data,$example);
	  $data1 = "[[[".ltrim($example[1][0],"[");
	  $data2 = explode("[[[",$data1);
	  $num = count(array_filter($data2));
		foreach($data2 as $key => $value){
		 	$data3 = explode("[[","[[".$value);
		 	foreach ($data3 as $k => $v) {
		 		preg_match_all("/\[\"(.*)\",/Us","[".$v, $match);
		 		if(!empty($match[1])){
		 			$str .= implode($match[1]," ")."@";
		 		}
		 	}
		}
		$data4 = trim($str,"@");
		$data5 = explode("@", $data4);
		$result = array_chunk($data5, 2);
		return $result;
	}

	/**
   * 获取简明释义
   * return array (x => "词性"，b => "附属")
   * 
	 **/

	private function getExplain(){
		$data = $this -> getContent();
		preg_match_all("/id\=\"en\-simple\-means\"\>(.*)\/Us",$data,$explain);
		$r_data = $explain[1][0];
		preg_match_all("/\\(?P.*)\<\/strong\>\(?P.*)\<\/span\>\<\/p\>/Us", $r_data, $a_data);
		preg_match_all("/\(?P[^\>]+)\：\(?P.*)\<\/a\>\<\/span\>/Us", $r_data, $b_data);
		
		$result = array();
		foreach ($a_data["adj"] as $key => $value) {
			$result[$value] = $a_data["name"][$key];
		}
		
		$word_b = array();
		foreach ($b_data["tag"] as $key => $value) {
			$word_b[$value] = strip_tags($b_data["word"][$key]);
		}
		
		$result_data = array("x" => $result,"b" => $word_b);

 		return $result_data;
	}


	/**
   * 获取同义词
   * return array(0 => "同义词", 1 => "反义词") 一般为多维数组
   * 
	 */

	private function getSynonym(){
		$data = $this -> getContent();
		preg_match_all("/id=\"en\-syn\-ant\"\>(.*)/Us",$data,$synonym);
		$content = $synonym[1][0];
		$data1 = explode("", $content);
		$result = array();
		$data2 = array();
		foreach ($data1 as $key => $value) {
			preg_match_all("/\(?P.*)\ \;\<\/strong\>\<\\>\\(?.*)\<\/ul\>/Us", $value, $r_data);
			$data2[$key]["adj"] = $r_data["adj"];
			$data2[$key]["content"] = $r_data["content"];
		}

		foreach ($data2 as $key => $value) {
			foreach ($value["content"] as $k => $v) {
				if(!empty($v)){
					preg_match_all("/\\(?P